<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chai-etal-2020-highway">
    <titleInfo>
        <title>Highway Transformer: Self-Gating Enhanced Self-Attentive Networks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yekun</namePart>
        <namePart type="family">Chai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shuo</namePart>
        <namePart type="family">Jin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xinwen</namePart>
        <namePart type="family">Hou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dan</namePart>
            <namePart type="family">Jurafsky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Chai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Natalie</namePart>
            <namePart type="family">Schluter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joel</namePart>
            <namePart type="family">Tetreault</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Self-attention mechanisms have made striking state-of-the-art (SOTA) progress in various sequence learning tasks, standing on the multi-headed dot product attention by attending to all the global contexts at different locations. Through a pseudo information highway, we introduce a gated component self-dependency units (SDU) that incorporates LSTM-styled gating units to replenish internal semantic importance within the multi-dimensional latent space of individual representations. The subsidiary content-based SDU gates allow for the information flow of modulated latent embeddings through skipped connections, leading to a clear margin of convergence speed with gradient descent algorithms. We may unveil the role of gating mechanism to aid in the context-based Transformer modules, with hypothesizing that SDU gates, especially on shallow layers, could push it faster to step towards suboptimal points during the optimization process.</abstract>
    <identifier type="citekey">chai-etal-2020-highway</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.616</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.616</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>6887</start>
            <end>6900</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Highway Transformer: Self-Gating Enhanced Self-Attentive Networks
%A Chai, Yekun
%A Jin, Shuo
%A Hou, Xinwen
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F chai-etal-2020-highway
%X Self-attention mechanisms have made striking state-of-the-art (SOTA) progress in various sequence learning tasks, standing on the multi-headed dot product attention by attending to all the global contexts at different locations. Through a pseudo information highway, we introduce a gated component self-dependency units (SDU) that incorporates LSTM-styled gating units to replenish internal semantic importance within the multi-dimensional latent space of individual representations. The subsidiary content-based SDU gates allow for the information flow of modulated latent embeddings through skipped connections, leading to a clear margin of convergence speed with gradient descent algorithms. We may unveil the role of gating mechanism to aid in the context-based Transformer modules, with hypothesizing that SDU gates, especially on shallow layers, could push it faster to step towards suboptimal points during the optimization process.
%R 10.18653/v1/2020.acl-main.616
%U https://aclanthology.org/2020.acl-main.616
%U https://doi.org/10.18653/v1/2020.acl-main.616
%P 6887-6900

Markdown (Informal)

[Highway Transformer: Self-Gating Enhanced Self-Attentive Networks](https://aclanthology.org/2020.acl-main.616) (Chai et al., ACL 2020)

• Highway Transformer: Self-Gating Enhanced Self-Attentive Networks (Chai et al., ACL 2020)

ACL

• Yekun Chai, Shuo Jin, and Xinwen Hou. 2020. Highway Transformer: Self-Gating Enhanced Self-Attentive Networks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6887–6900, Online. Association for Computational Linguistics.